%{search_type} search results

Machine learning has accelerated in several industries recently, enabling companies to automate decisions and act based on predicted futures. In time, nearly all major industries will embed ML into the core of their businesses, but right now the gap between companies that successfully adopt ML and those that fail continues to grow. This report examines why so many ML initiatives stall, especially at the stage of moving models from proof of concept to production. Authors Ben Epstein and Paige Roberts examine the strengths and weaknesses of data lake and data warehouse analytic architectures, including the ways that companies use them cooperatively in production. You'll learn how to merge these separate technology stacks into a unified architecture that will streamline the daily workflows of data scientists and data engineers, and facilitate the seamless transition of models from development into production. With this report, you'll explore: Why the unique challenges of MLOps have caused so many ML applications to fail The evolution of data warehouse and data lake architectures How a unified analytics architecture enables you to unite the workflows of business analysts and data scientists How this architecture helps you get new ML projects into production as easily as creating new tables on a dashboard The advantages of in-database ML, including enhanced security, speed and scalability, accessibility, governance, and production readiness.

• Part I: Machine Learning/Deep Learning in Socializing and Entertainment.- Part II: Machine Learning/Deep Learning in.- Part III: Machine Learning/Deep Learning in Security.- Part IV: Machine Learning/Deep Learning in Time Series Forecasting.- Part V: Machine Learning in Video Coding and Information Extraction.
• (source: Nielsen Book Data)

As the 4th Industrial Revolution is restructuring human societal organization into, so-called, "Society 5.0", the field of Machine Learning (and its sub-field of Deep Learning) and related technologies is growing continuously and rapidly, developing in both itself and towards applications in many other disciplines. Researchers worldwide aim at incorporating cognitive abilities into machines, such as learning and problem solving. When machines and software systems have been enhanced with Machine Learning/Deep Learning components, they become better and more efficient at performing specific tasks. Consequently, Machine Learning/Deep Learning stands out as a research discipline due to its worldwide pace of growth in both theoretical advances and areas of application, while achieving very high rates of success and promising major impact in science, technology and society. The book at hand aims at exposing its readers to some of the most significant Advances in Machine Learning/Deep Learning-based Technologies. The book consists of an editorial note and an additional ten (10) chapters, all invited from authors who work on the corresponding chapter theme and are recognized for their significant research contributions. In more detail, the chapters in the book are organized into five parts, namely (i) Machine Learning/Deep Learning in Socializing and Entertainment, (ii) Machine Learning/Deep Learning in Education, (iii) Machine Learning/Deep Learning in Security, (iv) Machine Learning/Deep Learning in Time Series Forecasting, and (v) Machine Learning in Video Coding and Information Extraction. This research book is directed towards professors, researchers, scientists, engineers and students in Machine Learning/Deep Learning-related disciplines. It is also directed towards readers who come from other disciplines and are interested in becoming versed in some of the most recent Machine Learning/Deep Learning-based technologies. An extensive list of bibliographic references at the end of each chapter guides the readers to probe further into the application areas of interest to them.
(source: Nielsen Book Data)

• Front Matter
• Supervised Machine Learning: Algorithms and Applications / Shruthi H Shetty, Sumiksha Shetty, Chandra Singh, Ashwath Rao
• Zonotic Diseases Detection Using Ensemble Machine Learning Algorithms / K Bhargavi
• Model Evaluation / Ravi Shekhar Tiwari
• Analysis of M-SEIR and LSTM Models for the Prediction of COVID-19 Using RMSLE / S Archith, C Yukta, HR Archana, HH Surendra
• The Significance of Feature Selection Techniques in Machine Learning / N Bharathi, BS Rishiikeshwer, T Aswin Shriram, B Santhi, GR Brindha
• Use of Machine Learning and Deep Learning in Healthcare-A Review on Disease Prediction System / R Radha, R Gopalakrishnan
• Detection of Diabetic Retinopathy Using Ensemble Learning Techniques / Anirban Dutta, Parul Agarwal, Anushka Mittal, Shishir Khandelwal, Shikha Mehta
• Machine Learning and Deep Learning for Medical Analysis-A Case Study on Heart Disease Data / AM Swetha, B Santhi, GR Brindha
• A Novel Convolutional Neural Network Model to Predict Software Defects / Kumar Rajnish, Vandana Bhattacharjee, Mansi Gupta
• Predictive Analysis of Online Television Videos Using Machine Learning Algorithms / Jeyavadhanam B Rebecca, VV Ramalingam, V Sugumaran, D Rajkumar
• A Combinational Deep Learning Approach to Visually Evoked EEG-Based Image Classification / Nandini Kumari, Shamama Anwar, Vandana Bhattacharjee
• Application of Machine Learning Algorithms With Balancing Techniques for Credit Card Fraud Detection: A Comparative Analysis / Shiksha
• Crack Detection in Civil Structures Using Deep Learning / Bijimalla Shiva Vamshi Krishna, BS Rishiikeshwer, J Sanjay Raju, N Bharathi, C Venkatasubramanian, GR Brindha
• Measuring Urban Sprawl Using Machine Learning / Keerti Kulkarni, P A Vijaya
• Application of Deep Learning Algorithms in Medical Image Processing: A Survey / B Santhi, AM Swetha, AM Ashutosh
• Simulation of Self-Driving Cars Using Deep Learning / M K Rahul, Praveen L Uppunda, Raju S Vinayaka, B Sumukh, C Gururaj
• Assistive Technologies for Visual, Hearing, and Speech Impairments: Machine Learning and Deep Learning Solutions / K C Shahira, C J Sruthi, A Lijiya
• Case Studies: Deep Learning in Remote Sensing / Jenifer A Emily, N Sudha
• Index

FUNDAMENTALS AND METHODS OF MACHINE AND DEEP LEARNING The book provides a practical approach by explaining the concepts of machine learning and deep learning algorithms, evaluation of methodology advances, and algorithm demonstrations with applications. Over the past two decades, the field of machine learning and its subfield deep learning have played a main role in software applications development. Also, in recent research studies, they are regarded as one of the disruptive technologies that will transform our future life, business, and the global economy. The recent explosion of digital data in a wide variety of domains, including science, engineering, Internet of Things, biomedical, healthcare, and many business sectors, has declared the era of big data, which cannot be analysed by classical statistics but by the more modern, robust machine learning and deep learning techniques. Since machine learning learns from data rather than by programming hard-coded decision rules, an attempt is being made to use machine learning to make computers that are able to solve problems like human experts in the field. The goal of this book is to present a??practical approach by explaining the concepts of machine learning and deep learning algorithms with applications. Supervised machine learning algorithms, ensemble machine learning algorithms, feature selection, deep learning techniques, and their applications are discussed. Also included in the eighteen chapters is unique information which provides a clear understanding of concepts by using algorithms and case studies illustrated with applications of machine learning and deep learning in different domains, including disease prediction, software defect prediction, online television analysis, medical image processing, etc. Each of the chapters briefly described below provides both a chosen approach and its implementation. Audience Researchers and engineers in artificial intelligence, computer scientists as well as software developers.

• Front Matter
• Supervised Machine Learning: Algorithms and Applications / Shruthi H Shetty, Sumiksha Shetty, Chandra Singh, Ashwath Rao
• Zonotic Diseases Detection Using Ensemble Machine Learning Algorithms / K Bhargavi
• Model Evaluation / Ravi Shekhar Tiwari
• Analysis of M-SEIR and LSTM Models for the Prediction of COVID-19 Using RMSLE / S Archith, C Yukta, HR Archana, HH Surendra
• The Significance of Feature Selection Techniques in Machine Learning / N Bharathi, BS Rishiikeshwer, T Aswin Shriram, B Santhi, GR Brindha
• Use of Machine Learning and Deep Learning in Healthcare-A Review on Disease Prediction System / R Radha, R Gopalakrishnan
• Detection of Diabetic Retinopathy Using Ensemble Learning Techniques / Anirban Dutta, Parul Agarwal, Anushka Mittal, Shishir Khandelwal, Shikha Mehta
• Machine Learning and Deep Learning for Medical Analysis-A Case Study on Heart Disease Data / AM Swetha, B Santhi, GR Brindha
• A Novel Convolutional Neural Network Model to Predict Software Defects / Kumar Rajnish, Vandana Bhattacharjee, Mansi Gupta
• Predictive Analysis of Online Television Videos Using Machine Learning Algorithms / Jeyavadhanam B Rebecca, VV Ramalingam, V Sugumaran, D Rajkumar
• A Combinational Deep Learning Approach to Visually Evoked EEG-Based Image Classification / Nandini Kumari, Shamama Anwar, Vandana Bhattacharjee
• Application of Machine Learning Algorithms With Balancing Techniques for Credit Card Fraud Detection: A Comparative Analysis / Shiksha
• Crack Detection in Civil Structures Using Deep Learning / Bijimalla Shiva Vamshi Krishna, BS Rishiikeshwer, J Sanjay Raju, N Bharathi, C Venkatasubramanian, GR Brindha
• Measuring Urban Sprawl Using Machine Learning / Keerti Kulkarni, P A Vijaya
• Application of Deep Learning Algorithms in Medical Image Processing: A Survey / B Santhi, AM Swetha, AM Ashutosh
• Simulation of Self-Driving Cars Using Deep Learning / M K Rahul, Praveen L Uppunda, Raju S Vinayaka, B Sumukh, C Gururaj
• Assistive Technologies for Visual, Hearing, and Speech Impairments: Machine Learning and Deep Learning Solutions / K C Shahira, C J Sruthi, A Lijiya
• Case Studies: Deep Learning in Remote Sensing / Jenifer A Emily, N Sudha
• Index

FUNDAMENTALS AND METHODS OF MACHINE AND DEEP LEARNING The book provides a practical approach by explaining the concepts of machine learning and deep learning algorithms, evaluation of methodology advances, and algorithm demonstrations with applications. Over the past two decades, the field of machine learning and its subfield deep learning have played a main role in software applications development. Also, in recent research studies, they are regarded as one of the disruptive technologies that will transform our future life, business, and the global economy. The recent explosion of digital data in a wide variety of domains, including science, engineering, Internet of Things, biomedical, healthcare, and many business sectors, has declared the era of big data, which cannot be analysed by classical statistics but by the more modern, robust machine learning and deep learning techniques. Since machine learning learns from data rather than by programming hard-coded decision rules, an attempt is being made to use machine learning to make computers that are able to solve problems like human experts in the field. The goal of this book is to present a??practical approach by explaining the concepts of machine learning and deep learning algorithms with applications. Supervised machine learning algorithms, ensemble machine learning algorithms, feature selection, deep learning techniques, and their applications are discussed. Also included in the eighteen chapters is unique information which provides a clear understanding of concepts by using algorithms and case studies illustrated with applications of machine learning and deep learning in different domains, including disease prediction, software defect prediction, online television analysis, medical image processing, etc. Each of the chapters briefly described below provides both a chosen approach and its implementation. Audience Researchers and engineers in artificial intelligence, computer scientists as well as software developers.

• An Introduction to Generative Adversarial Learning: Architectures and Applications.- Generative Adversarial Networks: A Survey on Training, Variants, and Applications.- Fair Data Generation and Machine Learning through Generative Adversarial Networks.
• (source: Nielsen Book Data)

This book provides a collection of recent research works addressing theoretical issues on improving the learning process and the generalization of GANs as well as state-of-the-art applications of GANs to various domains of real life. Adversarial learning fascinates the attention of machine learning communities across the world in recent years. Generative adversarial networks (GANs), as the main method of adversarial learning, achieve great success and popularity by exploiting a minimax learning concept, in which two networks compete with each other during the learning process. Their key capability is to generate new data and replicate available data distributions, which are needed in many practical applications, particularly in computer vision and signal processing. The book is intended for academics, practitioners, and research students in artificial intelligence looking to stay up to date with the latest advancements on GANs' theoretical developments and their applications.
(source: Nielsen Book Data)

• Introduction.- Components of ML.- The Landscape of ML.- Empirical Risk Minimization.- Gradient-Based Learning.- Model Validation and Selection.- Regularization.- Clustering.- Feature Learning.- Transparant and Explainable ML.
• (source: Nielsen Book Data)

Machine learning (ML) has become a commonplace element in our everyday lives and a standard tool for many fields of science and engineering. To make optimal use of ML, it is essential to understand its underlying principles. This book approaches ML as the computational implementation of the scientific principle. This principle consists of continuously adapting a model of a given data-generating phenomenon by minimizing some form of loss incurred by its predictions. The book trains readers to break down various ML applications and methods in terms of data, model, and loss, thus helping them to choose from the vast range of ready-made ML methods. The book's three-component approach to ML provides uniform coverage of a wide range of concepts and techniques. As a case in point, techniques for regularization, privacy-preservation as well as explainability amount to specific design choices for the model, data, and loss of a ML method. .
(source: Nielsen Book Data)

• Cover
• Copyright
• Table of Contents
• Preface
• Who Should Read This Book?
• Why I Wrote This Book
• Navigating This Book
• Technology You Need to Understand
• Conventions Used in This Book
• Using Code Examples
• O'Reilly Online Learning
• How to Contact Us
• Acknowledgements
• Chapter 1. Introduction to AI and Machine Learning
• What Is Artificial Intelligence?
• What Is Machine Learning?
• Moving from Traditional Programming to Machine Learning
• How Can a Machine Learn?
• Comparing Machine Learning with Traditional Programming
• Building and Using Models on Mobile

• Step 6: Call the Face Detector
• Step 7: Add the Bounding Rectangles
• Building a Face Detector App for iOS
• Step 1: Create the Project in Xcode
• Step 2: Using CocoaPods and Podfiles
• Step 3: Create the User Interface
• Step 4: Add the Application Logic
• Summary
• Chapter 4. Computer Vision Apps with ML Kit on Android
• Image Labeling and Classification
• Step 1: Create the App and Configure ML Kit
• Step 2: Create the User Interface
• Step 3: Add the Images as Assets
• Step 4: Load an Image to the ImageView
• Step 5: Write the Button Handler Code
• Next Steps

• Object Detection
• Step 1: Create the App and Import ML Kit
• Step 2: Create the Activity Layout XML
• Step 3: Load an Image into the ImageView
• Step 4: Set Up the Object Detector Options
• Step 5: Handling the Button Interaction
• Step 6: Draw the Bounding Boxes
• Step 7: Label the Objects
• Detecting and Tracking Objects in Video
• Exploring the Layout
• The GraphicOverlay Class
• Capturing the Camera
• The ObjectAnalyzer Class
• The ObjectGraphic Class
• Putting It All Together
• Summary
• Chapter 5. Text Processing Apps with ML Kit on Android
• Entity Extraction

• Start Creating the App
• Create the Layout for the Activity
• Write the Entity Extraction Code
• Putting It All Together
• Handwriting and Other Recognition
• Start the App
• Creating a Drawing Surface
• Parsing the Ink with ML Kit
• Smart Reply to Conversations
• Start the App
• Mock a Conversation
• Generating a Smart Reply
• Summary
• Chapter 6. Computer Vision Apps with ML Kit on iOS
• Image Labeling and Classification
• Step 1: Create the App in Xcode
• Step 2: Create the Podfile
• Step 3: Set Up the Storyboard
• Step 4: Edit the View Controller Code to Use ML Kit

AI is nothing without somewhere to run it. Now that mobile devices have become the primary computing device for most people, it's essential that mobile developers add AI to their toolbox. This insightful book is your guide to creating models and running them on popular mobile platforms such as iOS and Android. Laurence Moroney, lead AI advocate at Google, offers an introduction to machine learning techniques and tools, then walks you through writing Android and iOS apps powered by common ML models like computer vision and text recognition, using tools such as ML Kit, TensorFlow Lite, and Core ML. If you're a mobile developer, this book will help you take advantage of the ML revolution today. Explore the options for implementing ML and AI on mobile devices--and when to use each Create ML models for iOS and Android Write ML Kit and TensorFlow Lite apps for iOS and Android and Core ML/Create ML apps for iOS Understand how to choose the best techniques and tools for your use case: on-device inference versus cloud-based inference, high-level APIs versus low-level APIs, and more Learn privacy and ethics best practices for ML on devices.
(source: Nielsen Book Data)

Follow a hands-on approach to AutoML implementation and associated methodologies and get to grips with automated machine learning Key Features * Get up to speed with AutoML using the platform of your choice, such as OSS, Azure, AWS, or GCP * Eliminate mundane tasks in data engineering and reduce human errors in ML models that occur mainly due to manual steps * Make machine learning accessible for all users, helping promote a decentralized process Book Description Every machine learning engineer deals with systems that have hyperparameters, and the most basic task in automated machine learning (AutoML) is to automatically set these hyperparameters to optimize performance. The latest deep neural networks have a wide range of hyperparameters for their architecture, regularization, and optimization, which can be customized effectively to save time and effort. This book reviews the underlying techniques of automated feature engineering, model and hyperparameter tuning, gradient-based approaches, and more. You'll explore different ways of implementing these techniques in open-source tools. Next, you'll focus on enterprise tools, learning different ways of implementing AutoML in three major cloud service providers, including Microsoft Azure, Amazon Web Services (AWS), and the Google Cloud Platform. As you progress, you'll explore the features of cloud AutoML platforms by building machine learning models using AutoML. Later chapters will show you how to develop accurate models by automating time-consuming and repetitive tasks involved in the machine learning development lifecycle. By the end of this book, you'll be able to build and deploy automated machine learning models that are not only accurate, but also increase productivity, allow interoperability, and minimize featuring engineering tasks. What you will learn * Explore AutoML fundamentals, underlying methods, and techniques * Assess AutoML aspects such as algorithm selection, auto featurization, and hyperparameter tuning in an applied scenario and differentiate between cloud and OSS offerings * Implement AutoML in tools such as AWS, Azure, and GCP and while deploying ML models and pipelines * Build explainable AutoML pipelines with transparency * Understand automated feature engineering and time series forecasting * Automate data science modeling tasks to implement ML solutions easily and focus on more complex problems Who This Book Is For Citizen data scientists, machine learning developers, artificial intelligence enthusiasts, or anyone looking to automatically build machine learning models using the features offered by open-source tools, Microsoft Azure Machine Learning, Amazon Web Services (AWS), and Google Cloud Platform will find this book useful.
(source: Nielsen Book Data)

• Table of Contents Introduction to Automated Machine Learning Getting Started with AutoKeras Automating the Machine Learning Pipeline with AutoKeras Image Classification and Regression Using AutoKeras Text Classification and Regression Using AutoKeras Working with Structured Data Using AutoKeras Sentiment Analysis Using AutoKeras Topic Classification Using AutoKeras Working with Multi-Modal Data and Multi-Task Exporting and Visualizing the Models.
• (source: Nielsen Book Data)

Create better and easy-to-use deep learning models with AutoKeras Key Features Design and implement your own custom machine learning models using the features of AutoKeras Learn how to use AutoKeras for techniques such as classification, regression, and sentiment analysis Get familiar with advanced concepts as multi-modal, multi-task, and search space customization Book DescriptionAutoKeras is an AutoML open-source software library that provides easy access to deep learning models. If you are looking to build deep learning model architectures and perform parameter tuning automatically using AutoKeras, then this book is for you. This book teaches you how to develop and use state-of-the-art AI algorithms in your projects. It begins with a high-level introduction to automated machine learning, explaining all the concepts required to get started with this machine learning approach. You will then learn how to use AutoKeras for image and text classification and regression. As you make progress, you'll discover how to use AutoKeras to perform sentiment analysis on documents. This book will also show you how to implement a custom model for topic classification with AutoKeras. Toward the end, you will explore advanced concepts of AutoKeras such as working with multi-modal data and multi-task, customizing the model with AutoModel, and visualizing experiment results using AutoKeras Extensions. By the end of this machine learning book, you will be able to confidently use AutoKeras to design your own custom machine learning models in your company. What you will learn Set up a deep learning workstation with TensorFlow and AutoKeras Automate a machine learning pipeline with AutoKeras Create and implement image and text classifiers and regressors using AutoKeras Use AutoKeras to perform sentiment analysis of a text, classifying it as negative or positive Leverage AutoKeras to classify documents by topics Make the most of AutoKeras by using its most powerful extensions Who this book is forThis book is for machine learning and deep learning enthusiasts who want to apply automated ML techniques to their projects. Prior basic knowledge of Python programming and machine learning is expected to get the most out of this book.
(source: Nielsen Book Data)

• Chapter 1: What is Machine Learning (ML)? Basics of Java Script (JS) Programming in the browser using Java Script Graphics and Interactive processing in the browser using Java Script libraries Getting started with P5.JS and ML5.JS References Chapter 2: Human Pose Estimation in the Browser Browser based data processing Posenet vs Openpose models Human pose estimation using ML5.Posenet Inputs, Outputs and Data structures of Posenet model References Chapter 3: Human Pose Classification
• Classification techniques using ML Neural Network in the browser Human Pose classification based on the outputs of Posenet model Consideration of poses using Confidence scores of Posenet model Storage of data using JSON formats related to the outputs of Posenet model References Chapter 4: Gait Analysis Normal vs Abnormal Gait patterns Determination of Gait patterns using threshold values of the models User Interface design and development for monitoring of Gait patterns Real-Time data visualization of the Gait patterns on the browser References Chapter 5: Future Possible Applications of Key Concepts.
• (source: Nielsen Book Data)

Apply Artificial Intelligence techniques in the browser or on resource constrained computing devices. Machine learning (ML) can be an intimidating subject until you know the essentials and for what applications it works. This book takes advantage of the intricacies of the ML processes by using a simple, flexible and portable programming language such as JavaScript to work with more approachable, fundamental coding ideas. Using JavaScript programming features along with standard libraries, you'll first learn to design and develop interactive graphics applications. Then move further into neural systems and human pose estimation strategies. For training and deploying your ML models in the browser, TensorFlow.js libraries will be emphasized. After conquering the fundamentals, you'll dig into the wilderness of ML. Employ the ML and Processing (P5) libraries for Human Gait analysis. Building up Gait recognition with themes, you'll come to understand a variety of ML implementation issues. For example, you'll learn about the classification of normal and abnormal Gait patterns. With Beginning Machine Learning in the Browser, you'll be on your way to becoming an experienced Machine Learning developer. What You'll Learn Work with ML models, calculations, and information gathering Implement TensorFlow.js libraries for ML models Perform Human Gait Analysis using ML techniques in the browser Who This Book Is For Computer science students and research scholars, and novice programmers/web developers in the domain of Internet Technologies.
(source: Nielsen Book Data)

• Part I. Concepts of Deep Learning: Recognition Systems
• Emotion Recognition from Speech Using Deep Neural Network
• Text-Independent Speaker Recognition Using Deep Learning
• A Qualitative and Quantitative Research of Machine Learning Algorithms for Gait Analysis and Recognition
• Emotion Recognition from Speech Signals Using Machine Learning and Deep Learning Techniques
• Micro-expression Detection Using Main Directional Maximal Differential Analysis (MDMD) Method
• Part II. Concepts of Deep Learning: Healthcare Systems
• Survival Prediction of Cancer Patient Using Machine Learning
• Skin Lesion Segmentation Using Deep Convolutional Networks
• Bone Cancer Survivability Prognosis with KNN and Genetic Algorithms
• BeamAtt: Generating Medical Diagnosis from Chest X-Rays Using Sampling-Based Intelligence
• Part III. Real-Time Applications of Deep Learning
• CNN-Based Driver Drowsiness Detection System
• Forecasting Using Deep Learning Approaches
• A Low-Cost IOT and Deep Learning Enabled Precision Agriculture Support System for Indian Diverse Environment.

This book provides readers with a comprehensive and recent exposition in deep learning and its multidisciplinary applications, with a concentration on advances of deep learning architectures. The book discusses various artificial intelligence (AI) techniques based on deep learning architecture with applications in natural language processing, semantic knowledge, forecasting and many more. The authors shed light on various applications that can benefit from the use of deep learning in pattern recognition, person re-identification in surveillance videos, action recognition in videos, image and video captioning. The book also highlights how deep learning concepts can be interwoven with more modern concepts to yield applications in multidisciplinary fields. Presents a comprehensive look at deep learning and its multidisciplinary applications, concentrating on advances of deep learning architectures; Includes a survey of deep learning problems and solutions, identifying the main open issues, innovations and latest technologies; Shows industrial deep learning in practice with examples/cases, efforts, challenges, and strategic approaches.
(source: Nielsen Book Data)

• Chapter 1 Introduction. 1
• 1.1
• AI's Historical Changes 1
• 1.2
• What Is Deep Learning?. 3
• 1.3
• Practical Applications of Deep Learning. 4
• 1.4
• Structure of the Book. 7
• 1.5
• Introduction to MindSpore. 7
• Chapter 2 Deep Learning Basics. 18
• 2.1
• Regression Algorithms. 18
• 2.2
• Gradient Descent 21
• 2.3
• Classification Algorithms. 25
• 2.4
• Overfitting and Underfitting. 28
• Chapter 3 DNN.. 32
• 3.1
• Feedforward Network. 32
• 3.2
• Backpropagation. 34
• 3.3
• Generalization Ability. 38
• 3.4
• Implementing Simple Neural Networks Using MindSpore. 39
• Chapter 4 Training of DNNs. 45
• 4.1
• Main Challenges to Deep Learning Systems 45
• 4.2
• Regularization. 48
• 4.3
• Dropout 51
• 4.4
• Adaptive Learning Rate. 55
• 4.5
• Batch Normalization. 59
• 4.6
• Implementing DNNs Using MindSpore. 61
• Chapter 5 Convolutional Neural Network. 66
• 5.1
• Convolution. 66
• 5.2
• Pooling. 69
• 5.3
• Residual Network. 71
• 5.4
• Application: Image Classification. 74
• 5.5
• Implementing Image Classification Based on the DNN Using MindSpore. 79
• Chapter 6 RNN.. 89
• 6.1
• Overview.. 89
• 6.2
• Deep RNN.. 90
• 6.3
• Challenges of Long-Term Dependency. 91
• 6.4
• LSTM Network and GRU.. 93
• 6.5
• Application: Text Prediction. 96
• 6.6
• Implementing Text Prediction Based on LSTM Using MindSpore. 97
• Chapter 7 Unsupervised Learning: Word Vector. 101
• 7.1
• Word2Vec. 102
• 7.2
• GloVe. 114
• 7.3
• Transformer 121
• 7.4
• BERT.. 130
• 7.5
• Comparison Between Typical Word Vector Generation Algorithms. 137
• 7.6
• Application: Automatic Question Answering. 139
• 7.7
• Implementing BERT-based Automatic Answering Using MindSpore. 154
• Chapter 8 Unsupervised Learning: Graph Vector. 159
• 8.1
• Graph Vector Overview.. 159
• 8.2
• DeepWalk Algorithm... 161
• 8.3
• LINE Algorithm... 166
• 8.4
• Node2Vec Algorithm... 170
• 8.5
• GCN Algorithm... 174
• 8.6
• GAT Algorithm... 179
• 8.7
• Application: Recommendation System.. 183
• Chapter 9 Unsupervised Learning: Deep Generative Model 191
• 9.1
• Variational Autoencoder 191
• 9.2
• Generative Adversarial Network. 200
• 9.3
• Application: Data Augmentation. 208
• 9.4
• Implementing GAN-based Data Augmentation Using MindSpore. 221
• Chapter 10 Deep Reinforcement Learning. 225
• 10.1
• Basic Concepts of Reinforcement Learning. 225
• 10.2
• Basic Solution Method. 230
• 10.3
• Deep Reinforcement Learning Algorithm... 235
• 10.4
• Latest Applications. 247
• 10.5
• Implementing DQN-based Game Using MindSpore. 253
• Chapter 11 Automated Machine Learning. 255
• 11.1
• AutoML Framework. 255
• 11.2
• Existing AutoML Systems. 278
• 11.3
• Meta Learning. 288
• 11.4
• Implementing AutoML Using MindSpore. 294
• Chapter 12 Device-Cloud Collaboration. 302
• 12.1
• On-device Inference. 302
• 12.2
• Device-Cloud Transfer Learning. 304
• 12.3
• Device-Cloud Federated Learning. 308
• 12.4
• Device-Cloud Collaboration Framework. 313
• Chapter 13 Deep Learning Visualization. 322
• 13.1
• Overview.. 322
• 13.2
• MindSpore Visualization. 337
• Chapter 14 Data Preparation for Deep Learning. 354
• 14.1
• Overview of Data Format 354
• 14.2
• Data Format in Deep Learning. 355
• 14.3
• Common Data Formats for Deep Learning. 362
• 14.4
• Training Data Preparation Using the MindSpore Data Format 377
• .
• (source: Nielsen Book Data)

This book systematically introduces readers to the theory of deep learning and explores its practical applications based on the MindSpore AI computing framework. Divided into 14 chapters, the book covers deep learning, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), unsupervised learning, deep reinforcement learning, automated machine learning, device-cloud collaboration, deep learning visualization, and data preparation for deep learning. To help clarify the complex topics discussed, this book includes numerous examples and links to online resources.
(source: Nielsen Book Data)

• Table of Contents PyTorch Lightning Adventure Getting Off the Ground with Your First Deep Learning Model Transfer Learning Using Pre-Trained Models Ready-to- Use Models from Bolts Time Series Models Deep Generative Models Semi-Supervised Learning Self-Supervised Learning Deploying and Scoring Models Scaling and Managing Training.
• (source: Nielsen Book Data)

Build, train, deploy, and scale deep learning models quickly and accurately, improving your productivity using the lightweight PyTorch Wrapper Key Features Become well-versed with PyTorch Lightning architecture and learn how it can be implemented in various industry domains Speed up your research using PyTorch Lightning by creating new loss functions, networks, and architectures Train and build new algorithms for massive data using distributed training Book DescriptionPyTorch Lightning lets researchers build their own Deep Learning (DL) models without having to worry about the boilerplate. With the help of this book, you'll be able to maximize productivity for DL projects while ensuring full flexibility from model formulation through to implementation. You'll take a hands-on approach to implementing PyTorch Lightning models to get up to speed in no time. You'll start by learning how to configure PyTorch Lightning on a cloud platform, understand the architectural components, and explore how they are configured to build various industry solutions. Next, you'll build a network and application from scratch and see how you can expand it based on your specific needs, beyond what the framework can provide. The book also demonstrates how to implement out-of-box capabilities to build and train Self-Supervised Learning, semi-supervised learning, and time series models using PyTorch Lightning. As you advance, you'll discover how generative adversarial networks (GANs) work. Finally, you'll work with deployment-ready applications, focusing on faster performance and scaling, model scoring on massive volumes of data, and model debugging. By the end of this PyTorch book, you'll have developed the knowledge and skills necessary to build and deploy your own scalable DL applications using PyTorch Lightning. What you will learn Customize models that are built for different datasets, model architectures, and optimizers Understand how a variety of Deep Learning models from image recognition and time series to GANs, semi-supervised and self-supervised models can be built Use out-of-the-box model architectures and pre-trained models using transfer learning Run and tune DL models in a multi-GPU environment using mixed-mode precisions Explore techniques for model scoring on massive workloads Discover troubleshooting techniques while debugging DL models Who this book is forThis deep learning book is for citizen data scientists and expert data scientists transitioning from other frameworks to PyTorch Lightning. This book will also be useful for deep learning researchers who are just getting started with coding for deep learning models using PyTorch Lightning. Working knowledge of Python programming and an intermediate-level understanding of statistics and deep learning fundamentals is expected.
(source: Nielsen Book Data)

Die Design Patterns in diesem Buch zeigen praxiserprobte Methoden und Lösungen für wiederkehrende Aufgaben beim Machine Learning. Die Autoren, drei Machine-Learning-Experten bei Google, beschreiben bewährte Herangehensweisen, um Data Scientists bei der Lösung gängiger Probleme im gesamten ML-Prozess zu unterstützen. Die Patterns bündeln die Erfahrungen von Hunderten von Experten und bieten einfache, zugängliche Best Practices. In diesem Buch finden Sie detaillierte Erläuterungen zu 30 Patterns für diese Themen: Daten- und Problemdarstellung, Operationalisierung, Wiederholbarkeit, Reproduzierbarkeit, Flexibilität, Erklärbarkeit und Fairness. Jedes Pattern enthält eine Beschreibung des Problems, eine Vielzahl möglicher Lösungen und Empfehlungen für die Auswahl der besten Technik für Ihre Situation.

It's time to dispel the myth that machine learning is difficult. Grokking Machine Learning teaches you how to apply ML to your projects using only standard Python code and high school-level math. No specialist knowledge is required to tackle the hands-on exercises using readily available machine learning tools! In Grokking Machine Learning, expert machine learning engineer Luis Serrano introduces the most valuable ML techniques and teaches you how to make them work for you. Practical examples illustrate each new concept to ensure you're grokking as you go. You'll build models for spam detection, language analysis, and image recognition as you lock in each carefully-selected skill. Packed with easy-to-follow Python-based exercises and mini-projects, this book sets you on the path to becoming a machine learning expert. Key Features * Different types of machine learning, including supervised and unsupervised learning * Algorithms for simplifying, classifying, and splitting data * Machine learning packages and tools * Hands-on exercises with fully-explained Python code samples For readers with intermediate programming knowledge in Python or a similar language. About the technology Machine learning is a collection of mathematically-based techniques and algorithms that enable computers to identify patterns and generate predictions from data. This revolutionary data analysis approach is behind everything from recommendation systems to self-driving cars, and is transforming industries from finance to art. Luis G. Serrano has worked as the Head of Content for Artificial Intelligence at Udacity and as a Machine Learning Engineer at Google, where he worked on the YouTube recommendations system. He holds a PhD in mathematics from the University of Michigan, a Bachelor and Masters from the University of Waterloo, and worked as a postdoctoral researcher at the University of Quebec at Montreal. He shares his machine learning expertise on a YouTube channel with over 2 million views and 35 thousand subscribers, and is a frequent speaker at artificial intelligence and data science conferences.
(source: Nielsen Book Data)

• Introduction.- Background.- Hardware-Aware Cost Models.- Hardware-Aware Bayesian Networks for Sensor Front-End Quality Scaling.- Hardware-Aware Probabilistic Circuits.- Run-Time Strategies.- Conclusions.
• (source: Nielsen Book Data)

This book proposes probabilistic machine learning models that represent the hardware properties of the device hosting them. These models can be used to evaluate the impact that a specific device configuration may have on resource consumption and performance of the machine learning task, with the overarching goal of balancing the two optimally. The book first motivates extreme-edge computing in the context of the Internet of Things (IoT) paradigm. Then, it briefly reviews the steps involved in the execution of a machine learning task and identifies the implications associated with implementing this type of workload in resource-constrained devices. The core of this book focuses on augmenting and exploiting the properties of Bayesian Networks and Probabilistic Circuits in order to endow them with hardware-awareness. The proposed models can encode the properties of various device sub-systems that are typically not considered by other resource-aware strategies, bringing about resource-saving opportunities that traditional approaches fail to uncover. The performance of the proposed models and strategies is empirically evaluated for several use cases. All of the considered examples show the potential of attaining significant resource-saving opportunities with minimal accuracy losses at application time. Overall, this book constitutes a novel approach to hardware-algorithm co-optimization that further bridges the fields of Machine Learning and Electrical Engineering.
(source: Nielsen Book Data)

• 1. Ambitions and Goals of Machine Learning
• 2. Probabilities: Bayesian Classifiers
• 3. Similarities: Nearest-Neighbor Classifiers
• 4. Inter-Class Boundaries: Linear and Polynomial Classifiers
• 5. Decision Trees
• 6. Artificial Neural Networks
• 7. Computational Learning Theory
• 8. Experience from Historical Applications
• 9. Voting Assemblies and Boosting
• 10. Classifiers in the Form of Rule-Sets
• 11. Practical Issues to Know About
• 12. Performance Evaluation
• 13. Statistical Significance
• 14. Induction in Multi-Label Domains
• 15. Unsupervised Learning
• 16. Deep Learning
• 17. Reinforcement Learning: N-Armed Bandits and Episodes
• 18. Reinforcement Learning: From TD(0) to Deep-Q-Learning
• 19. Temporal Learning
• 20. Hidden Markov Models
• 21. Genetic Algorithm
• Bibliography
• Index.

This textbook offers a comprehensive introduction to Machine Learning techniques and algorithms. This Third Edition covers newer approaches that have become highly topical, including deep learning, and auto-encoding, introductory information about temporal learning and hidden Markov models, and a much more detailed treatment of reinforcement learning. The book is written in an easy-to-understand manner with many examples and pictures, and with a lot of practical advice and discussions of simple applications. The main topics include Bayesian classifiers, nearest-neighbor classifiers, linear and polynomial classifiers, decision trees, rule-induction programs, artificial neural networks, support vector machines, boosting algorithms, unsupervised learning (including Kohonen networks and auto-encoding), deep learning, reinforcement learning, temporal learning (including long short-term memory), hidden Markov models, and the genetic algorithm. Special attention is devoted to performance evaluation, statistical assessment, and to many practical issues ranging from feature selection and feature construction to bias, context, multi-label domains, and the problem of imbalanced classes.
(source: Nielsen Book Data)

Recent advances in machine learning have lowered the barriers to creating and using ML models. But understanding what these models are doing has only become more difficult. We discuss technological advances with little understanding of how they work and struggle to develop a comfortable intuition for new functionality. In this report, authors Austin Eovito and Marina Danilevsky from IBM focus on how to think about neural network-based language model architectures. They guide you through various models (neural networks, RNN/LSTM, encoder-decoder, attention/transformers) to convey a sense of their abilities without getting entangled in the complex details. The report uses simple examples of how humans approach language in specific applications to explore and compare how different neural network-based language models work. This report will empower you to better understand how machines understand language. Dive deep into the basic task of a language model to predict the next word, and use it as a lens to understand neural network language models Explore encoder-decoder architecture through abstractive text summarization Use machine translation to understand the attention mechanism and transformer architecture Examine the current state of machine language understanding to discern what these language models are good at and their risks and weaknesses.

• 1 Introduction.- 2 Model Selection and Evaluation.- 3 Linear Models.- 4 Decision Trees.- 5 Neural Networks.- 6 Support Vector Machine.- 7 Bayes Classifiers.- 8 Ensemble Learning.- 9 Clustering.- 10 Dimensionality Reduction and Metric Learning.- 11 Feature Selection and Sparse Learning.- 12 Computational Learning Theory.- 13 Semi-Supervised Learning.- 14 Probabilistic Graphical Models.- 15 Rule Learning.- 16 Reinforcement Learning.
• (source: Nielsen Book Data)

Machine Learning, a vital and core area of artificial intelligence (AI), is propelling the AI field ever further and making it one of the most compelling areas of computer science research. This textbook offers a comprehensive and unbiased introduction to almost all aspects of machine learning, from the fundamentals to advanced topics. It consists of 16 chapters divided into three parts: Part 1 (Chapters 1-3) introduces the fundamentals of machine learning, including terminology, basic principles, evaluation, and linear models; Part 2 (Chapters 4-10) presents classic and commonly used machine learning methods, such as decision trees, neural networks, support vector machines, Bayesian classifiers, ensemble methods, clustering, dimension reduction and metric learning; Part 3 (Chapters 11-16) introduces some advanced topics, covering feature selection and sparse learning, computational learning theory, semi-supervised learning, probabilistic graphical models, rule learning, and reinforcement learning. Each chapter includes exercises and further reading, so that readers can explore areas of interest. The book can be used as an undergraduate or postgraduate textbook for computer science, computer engineering, electrical engineering, data science, and related majors. It is also a useful reference resource for researchers and practitioners of machine learning.
(source: Nielsen Book Data)